digital-human

Generate talking digital-human videos from an image and audio via Volcengine OmniHuman1.5.

27|9|Updated Jan 25, 2026

Search Tags:#video-generation #avatar #volcengine #omnihuman #digital-human

Ready to run

npx skills add https://github.com/Leoyishou/personal-ai-company --skill digital-human

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: digital-human
Source: https://github.com/Leoyishou/personal-ai-company/tree/main/claude-global/skills/digital-human
Command: npx skills add https://github.com/Leoyishou/personal-ai-company --skill digital-human

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, python-dotenv, and includes scripts (resource) components.

What problem does it solve?

This skill automates the generation of talking digital-human videos from a single IP image and audio, removing manual, time-consuming animation and video production steps.

Core Features & Use Cases

Generate lip-synced, motion-aware talking digital-human videos using Volcengine OmniHuman1.5.
Supports URL inputs or local files uploaded to Supabase, enabling flexible workflows for avatars, marketing videos, or interactive characters.
Use cases include virtual presenters for branding, AI-assisted storytelling, and educational content.

Quick Start

Provide image_url and audio_url to generate a talking digital human video.

Frequently Asked Questions about digital-human

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate a talking digital human video from an image and audio file?▼

To generate a talking digital human video, provide a single IP image and an audio file as URL inputs to the Volcengine OmniHuman1.5 API. The system processes these inputs to create a lip-synced, motion-aware video avatar.

Can I use local image and audio uploads to create a digital human?▼

Yes, you can use local uploads to create a digital human by uploading your files to Supabase. This generates the necessary URLs to pass to the Volcengine OmniHuman1.5 API for video generation.

Do I need Volcengine credentials to produce AI avatar videos?▼

Yes, Volcengine credentials are required to produce AI avatar videos. You must configure the VolcEngine API credentials properly in your environment using python-dotenv to authenticate the OmniHuman1.5 requests.

What are the best use cases for generating digital human videos with OmniHuman?▼

The best use cases for generating digital human videos include creating virtual presenters for branding, AI-assisted storytelling, marketing campaigns, and educational content. It automates animation steps for quick avatar production.

Can I customize the output sizing and prompts when creating a talking digital human?▼

Yes, you can customize the output sizing and prompts when creating a talking digital human. The skill allows these customization options alongside the core image and audio URL inputs for the Volcengine API.

Why is my digital human video generation not working?▼

Digital human video generation may not work if Volcengine credentials are missing or improperly configured. Ensure your python-dotenv environment is set up correctly and that your image and audio URLs are accessible.